ICE-ID: A Novel Historical Census Data Benchmark Comparing NARS against LLMs, \& a ML Ensemble on Longitudinal Identity Resolution
This provides a new benchmark for identity resolution in longitudinal data, enabling cross-disciplinary research in data linkage and historical analytics, though it is incremental in applying existing methods to a new domain-specific dataset.
The authors tackled the problem of historical identity resolution by introducing ICE-ID, a benchmark dataset of Icelandic census records from 1703-1920, and found that NARS, a novel AI framework, achieved state-of-the-art performance on this task.
We introduce ICE-ID, a novel benchmark dataset for historical identity resolution, comprising 220 years (1703-1920) of Icelandic census records. ICE-ID spans multiple generations of longitudinal data, capturing name variations, demographic changes, and rich genealogical links. To the best of our knowledge, this is the first large-scale, open tabular dataset specifically designed to study long-term person-entity matching in a real-world population. We define identity resolution tasks (within and across census waves) with clearly documented metrics and splits. We evaluate a range of methods: handcrafted rule-based matchers, a ML ensemble as well as LLMs for structured data (e.g. transformer-based tabular networks) against a novel approach to tabular data called NARS (Non-Axiomatic Reasoning System) - a general-purpose AI framework designed to reason with limited knowledge and resources. Its core is Non-Axiomatic Logic (NAL), a term-based logic. Our experiments show that NARS is suprisingly simple and competitive with other standard approaches, achieving SOTA at our task. By releasing ICE-ID and our code, we enable reproducible benchmarking of identity resolution approaches in longitudinal settings and hope that ICE-ID opens new avenues for cross-disciplinary research in data linkage and historical analytics.